© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3728
    Prev
    Next
    INDEX
    Explanations

    references to various financial institutions and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to financial institutions and accountability organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gotten
    -0.80
    allo
    -0.77
    olson
    -0.77
    netflix
    -0.73
    go
    -0.71
    lc
    -0.69
    deck
    -0.67
    icular
    -0.67
     Giul
    -0.67
    escal
    -0.66
    POSITIVE LOGITS
     Disorders
    1.19
     Flavoring
    1.16
     Development
    1.16
     Authority
    1.14
     Association
    1.13
     Affairs
    1.11
     Assistance
    1.09
     Accountability
    1.08
     Services
    1.06
     Digest
    1.06
    Activations Density 0.079%

    No Known Activations